Agent Development

Create and validate Claude Code plugin agents with frontmatter, system prompts, and triggering examples.

Updated Aug 3, 2026
One-click install
npx skills add https://github.com/Yvesdefaria/GymLab --skill agent-development-yvesdefaria
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Agent Development
Source: https://github.com/Yvesdefaria/GymLab/tree/main/.opencode/skills/agent-development
Command: npx skills add https://github.com/Yvesdefaria/GymLab --skill agent-development-yvesdefaria

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Writing Claude Code plugin agents requires precise YAML frontmatter, well-structured system prompts, and triggering examples, and mistakes in any of these cause agents to fail to trigger or behave unpredictably. ## Core Features & Use Cases - Agent File Authoring: Provides the complete agent markdown format covering name, description, model, color, and tools frontmatter fields with validation rules. - System Prompt Design Patterns: Supplies templates for analysis, generation, validation, and orchestration agents with responsibilities, process steps, and output formats. - Triggering Example Guidance: Explains how to write example blocks with context, user messages, and commentary so agents trigger reliably. - Use Case: When you need a code review agent for your plugin, follow the templates to create agents/code-reviewer.md, then run scripts/validate-agent.sh to confirm the structure and fields are correct. ## Quick Start Create a code review agent for my Claude Code plugin and validate the agent file structure.

Frequently Asked Questions about Agent Development

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create an agent for a Claude Code plugin?

Create a markdown file in the plugin's agents directory with YAML frontmatter containing name, description, model, and color fields, followed by a system prompt body. The description must include triggering conditions and example blocks showing when the agent activates.

What frontmatter fields are required for a Claude Code agent?

Four fields are required: name (lowercase with hyphens, 3-50 characters), description (triggering conditions with examples), model (inherit, sonnet, opus, or haiku), and color (blue, cyan, green, yellow, magenta, or red). The tools field is optional for restricting access.

How do I write triggering examples for an agent description?

Use example blocks containing Context, a user message, an assistant response, and commentary explaining why the agent triggers. Include 2-4 examples covering explicit requests, proactive triggering, and varied phrasings of the same intent.

Why is my Claude Code agent not triggering?

Triggering fails when description examples lack relevant keywords, contexts do not match real usage, or commentary omits the triggering logic. Add more examples with different phrasings and ensure each shows the assistant invoking the agent.

How long should an agent system prompt be?

System prompts should be between 20 and 10,000 characters, with 500-3,000 characters being typical. Write in second person, include core responsibilities, a step-by-step process, quality standards, output format, and edge case handling.